English
Every 📧
Report

Every 📧

@every

AI-pill your whole company with the Every Agent: https://t.co/ki3hyz8sVP

141 Following58.3K Followers7.6K Posts
  1. Every 📧@every
    Introducing: The @Every agent, the fastest way to AI-pill your company, now officially out of beta. With personal agent use, no one can see how their teammates are working with AI. With one “company agent” in @SlackHQ, they can. The Every agent comes loaded with the skills and workflows we use to run Every, and each person on your team gets $15 in free credits to try it. Install @Every in @SlackHQ today:
    Dan Shipper @danshipper
    BREAKING: Introducing the @Every Agent—an agentic coworker in Slack built to help you AI-pill your company. It comes with: - Everything you'd expect from a premium company agent. You can delegate difficult, long-running—like opening PRs, writing reports from large datasets, and monitoring social or customer feedback—and get high-quality results all from Slack - Every's best workflows, pre-installed and always updated. Compound Engineering to Compound Writing. We add more all the time. - Personalized Frontier Alerts. to help you keep up with new models. When we drop a Vibe Check, the Every Agent will read it and let you know if the new model is relevant to your workflow. - Zero markup on tokens. What we pay is what you pay—as token prices go down, so does your bill. You can try it today with $15 in free credits per person, up to $500 per workspace. After that: it comes with your $30/month Every subscription, plus tokens at cost. Add the Every Agent to Slack: Why it's hard to AI-pill your coworkers If you’re the AI-pilled one at work, you know the problem: you discover something incredible in Claude or Codex, but getting your coworkers to try it is another matter. The problem is that most of your AI use is invisible. You do it alone, in a terminal or a chat window. Your coworkers see the finished report or the five new ads, but they never see the request that produced them, or the corrections you made along the way. When you describe it afterward, it sounds like magic, but nobody learns a magic trick without seeing how it’s done. Why a company agent, in Slack, solves this problem When you use a company agent like the @every agent you go from prompting in private, to prompting in public. In a Slack channel, a coworker who would never open a terminal scrolls past a thread with your agent interaction and thinks: I could do that too. This lets you show instead of tell your coworkers about your discoveries. New AI tools and workflows then spread naturally and virally across your organization. That's why we made the @every agent for ourselves—and why we're releasing it to you today. Add the Every Agent to Slack:
    432013.5K
  2. Dan Shipper✓@danshipper
    BREAKING: Introducing the @Every Agent—an agentic coworker in Slack built to help you AI-pill your company. It comes with: - Everything you'd expect from a premium company agent. You can delegate difficult, long-running—like opening PRs, writing reports from large datasets, and monitoring social or customer feedback—and get high-quality results all from Slack - Every's best workflows, pre-installed and always updated. Compound Engineering to Compound Writing. We add more all the time. - Personalized Frontier Alerts. to help you keep up with new models. When we drop a Vibe Check, the Every Agent will read it and let you know if the new model is relevant to your workflow. - Zero markup on tokens. What we pay is what you pay—as token prices go down, so does your bill. You can try it today with $15 in free credits per person, up to $500 per workspace. After that: it comes with your $30/month Every subscription, plus tokens at cost. Add the Every Agent to Slack: Why it's hard to AI-pill your coworkers If you’re the AI-pilled one at work, you know the problem: you discover something incredible in Claude or Codex, but getting your coworkers to try it is another matter. The problem is that most of your AI use is invisible. You do it alone, in a terminal or a chat window. Your coworkers see the finished report or the five new ads, but they never see the request that produced them, or the corrections you made along the way. When you describe it afterward, it sounds like magic, but nobody learns a magic trick without seeing how it’s done. Why a company agent, in Slack, solves this problem When you use a company agent like the @every agent you go from prompting in private, to prompting in public. In a Slack channel, a coworker who would never open a terminal scrolls past a thread with your agent interaction and thinks: I could do that too. This lets you show instead of tell your coworkers about your discoveries. New AI tools and workflows then spread naturally and virally across your organization. That's why we made the @every agent for ourselves—and why we're releasing it to you today. Add the Every Agent to Slack:
    Download
    421222754.5K
  3. Every 📧@every
    Many people are saying.
    Dan Shipper @danshipper
    if you're not livestreaming thesis on november 5th from @every FOR FREE what are you doing?
    0142K
  5. Dan Shipper✓@danshipper
    if you're not livestreaming thesis on november 5th from @every FOR FREE what are you doing?
    Download
    02134.2K
  8. Every 📧@every
    Over 80% of @AnthropicAI’s Q3 revenue came from models released in the previous six months. A $2 trillion valuation means betting it can keep making the next hit. And be worth about the GDP of Spain at the same time. @itsurboyevan breaks down the business behind the eye-popping numbers:
    Download
    0592.2K
  10. Every 📧@every
    An operator with an idea used to need a vendor to add the feature—or an engineer to help build it. @ArielleShipper can now build some of the systems she needs herself. As the models improve, she’s excited about how much more of her operational work she’ll be able to turn into tools. Watch the full episode:
    Download
    2272.9K
  11. Every 📧@every
    📣 Thesis: 2027 will be livestreamed for free 📣
    Dan Shipper @danshipper
    The bad news: Thesis: 2027 is sold out. The good news: you can watch it all live, for free. Next Thursday, join us for conversations with @joshm, @ivanhzhao, @ajambrosino, and a lot more. Plus, the Every team will be leading practical sessions on writing, engineering, and working with agents. To celebrate, we’re giving away $20,000 in credits and benefits from partners like @AnthropicAI, @NotionHQ, and @OpenAI to lucky viewers who join the livestream. Already an Every subscriber? You’ll still need to register for the livestream to win. Register and watch free here:
    0192.1K
  12. Every 📧@every
    .@hammer_mt starts a fresh chat for every task, even for the same project. He does this to avoid context rot, which happens when accumulated history makes AI responses worse. These are 7 tips for context engineering: 1. Start a new thread whenever the tone or type of task changes. 2. Keep memory turned off so irrelevant context can’t leak into the current conversation. 3. Only upload the documents the task needs. 4. Keep the preferences you always want—like spelling, tone, or length—in a saved document and paste them in at the top of every new chat. 5. Write the full brief before you start and put everything the model needs into the first message rather than drip-feeding it. 6. When the AI makes a mistake, go back and edit your previous message so it has no memory of doing anything wrong. 7. Before you leave a long thread, ask the model the question Mike has recommended when working on recurring tasks: What information would have been useful to know at the start of this task that would have eliminated several steps or mistakes? Get Mike’s new book, Context Engineering with DSPy: Read the full piece:
    Download
    44112K
  13. Dan Shipper✓@danshipper
    The bad news: Thesis: 2027 is sold out. The good news: you can watch it all live, for free. Next Thursday, join us for conversations with @joshm, @ivanhzhao, @ajambrosino, and a lot more. Plus, the Every team will be leading practical sessions on writing, engineering, and working with agents. To celebrate, we’re giving away $20,000 in credits and benefits from partners like @AnthropicAI, @NotionHQ, and @OpenAI to lucky viewers who join the livestream. Already an Every subscriber? You’ll still need to register for the livestream to win. Register and watch free here:
    Download
    688114.5K
  14. Every 📧@every
    ATTENDING: Fletcher Richman of @typedotcom will attend Thesis: 2027. Apply to attend Thesis, our inaugural conference on work and AI:
    Download
    1141.8K
  15. Every 📧@every
    A few weeks ago we launched the Every Agent, one Slack agent for the whole company. Here are @bigwilliestyle’s 3 rules for designing an agent the company can use: 1. Conversations: Help the agent follow a Slack thread. With a personal agent, the conversation is straightforward. You type, the model answers, and you’re done. In a Slack thread, anyone can jump in at any time. To feel like a coworker, a shared agent has to follow the conversation, even when several people are talking at once. Because we knew this was a likely point of failure, @paridhitweets and the team added a translation layer that organizes Slack messages for the model and sends its replies back to the thread. 2. Connections: Keep tasks running when logins change. For an agent to be useful, it has to reach the tools that people need. But each connection requires the agent to sign in to the tool through someone’s account. If that login breaks, it could stop everyone’s work. @leeknowlton has set up a task to connect to a “slot,” where any login that meets the task’s requirement can reside. When a login expires, the connection in the slot gets swapped out. Most people will never see any of this. Their automations will keep running as usual. 3. Permissions: Put access rules in code. When a company agent can reach everything the team has connected, each request raises two questions: Whose access is the agent using, and is the person asking allowed to use it? People treat Every Agent like a coworker, and human coworkers sometimes bend the rules. But an agent can’t make such judgments, and the rigidity can make it frustrating to work with. The rules about who can do what live in code, underneath the model, rather than in the instructions the model reads. This way, the model can’t be convinced to bend rules that it shouldn’t. Install the Every agent: Read more:
    Download
    1141.1K
  16. Every 📧@every
    Your AI bill tells you what you spent. What work did those tokens actually buy? @ArielleShipper demos Every’s usage dashboard, which breaks spending down by person, model, and effort level. A companion workflow groups sessions into types of work and asks the user to approve the categories—so they can judge whether the spending was worth it. Watch the full episode:
    Download
    52183.2K
  17. Every 📧@every
    We're hiring a marketing associate. Strong project management, clear writing, hands-on AI experience. Enthusiastic about managing chaos. NYC preferred; remote welcome. Apply here:
    1272.6K
  18. Every 📧@every
    Keeping up with every AI model can become a full-time distraction for a company. Every’s frontier team gives people like @danshipper room to experiment while the rest of the company builds products and serves customers. Some experiments become useful lessons. Others make their way into products and services once they’re ready for the wider team. Watch the full episode:
    Download
    131293.4K
  19. Every 📧@every
    Context Engineering With DSPy
    0081.2K
  20. Every 📧@every
    If you’ve just joined a company and are still figuring out who does what, try asking your company agent. That’s what happened to @beckyisj, who joined the team earlier this year. She asked the Every Agent who people were, their responsibilities, and what unfamiliar terms meant. Because the company shares one agent, it could draw on conversations and documents she hadn’t found yet. 3 prompts to try on day one: • I’ve just joined [team]. What are the main projects they are working on right now? • Who is [name], what do they own, and what should I ask them? • Summarize the last week of #[channel]. My role is [x], and my goals are [insert here]. Caveat: Don’t forget to check the answers with people, too. A misattributed transcript sent her to the wrong colleague, but they were able to point her to the right person. Install the Every agent: Read more:
    Download
    3251.8K
  21. Every 📧@every
    Every 📧
    RT @nathanbarry: The newsletter is dead. AI agents are going to read it before your subscribers do. At least, that’s @danshipper's take. As CEO of Every, a company that writes about AI and builds AI software, Dan's about as close to the cutting edge as anyone I know. I’ve spent 13 years building my career around email, so this was difficult to hear. But as much as I hate to admit it, I think Dan might be right. The good news is there’s still time to adapt. In this episode, Dan shares what you can start doing now to make sure your emails still reach your audience.
    040411
  22. Every 📧@every
    100 AI experiments won’t help your company if none of them land. @kieranklaassen’s advice for frontier teams: Listen to the people doing the work, make the experiments understandable, and help the useful ones get adopted. Dumping everything into a channel is easy. Integration is the job. Watch the full episode:
    Download
    94203.8K
  23. Every 📧@every
    Early this year we built Plus One, our personal-agent product. In May, we deleted 86,730 lines of its code because it wasn’t working. A personal bot like OpenClaw was too much work to run: Each agent lived on its own cloud computer, which was too high-maintenance. Many of us ended up abandoning our bots. For the bots that remained alive, we noticed that they were most useful when borrowed by other people. @tedescau connected his Plus One to our analytics tool, and people on the team asked it analytics questions. We decided to start over, making two changes: 1. We let Anthropic’s Claude Managed Agents take care of the infrastructure. 2. We replaced our fleet of personal agents with one shared company agent. @bigwilliestyle breaks down the process behind the creation of the Every Agent: Install the Every Agent:
    Download
    21101.5K
  24. Every 📧@every
    The raw material for an explainer video was already in @hammer_mt’s @SlackHQ messages and @meetgranola notes. He asked Opus to find the narrative, pull references to what he’d said, and cut a video explaining Checks, Every’s personal benchmark product. For someone busy running experiments, that makes it easier to tell the team what he’s been building. Watch the full episode:
    Download
    22154.1K
  26. Every 📧@every
    Before the CEO woke up, the Every Agent flagged a customer who was still waiting for their test results. The customer, a farmer, had paid for bovine parentage testing and was asking for an update. The only issue was the engineer in charge was out sick. Thankfully, the agent’s morning report connected those facts and suggested a coworker who could cover. That’s one example from FeanixBio, a 28-person cattle genetics startup serving about 35 family-owned farms. Its team uses the shared agent for task reports and vacation coverage, too. Install the Every Agent: Read more:
    Download
    0081.9K
  28. Every 📧@every
    What would it look like to manage coding agents at the level of goals and plans? @JannikJung built Minga to try it. He gives an orchestrator the requirements; it breaks the work into tasks, tracks dependencies, and starts work in the background. When it needs a decision or feedback on a UI, it brings him back in. Watch the full episode:
    Download
    174294.2K
  29. Every 📧@every
    Very little is free in NYC. But if you're a paid Every subscriber, our afterparty for Thesis: 2027 costs exactly $0. Your agent can work late. You have a party to go to. DJ. Passed bites. Open bar. And more. 🥳 Join us at Pioneer Works in Red Hook, Brooklyn. 🪩 November 5, 2026. 6–9 p.m. ET. 21+. 🎟️ RSVP:
    Download
    03162.1K
  30. Every 📧@every
    AI makes it easier to generate ideas. It also makes it easier to overwhelm everyone around you. @hammer_mt’s next job is making his experiments easier to absorb: turning the work into digestible videos and protecting his colleagues’ attention as his output grows. Watch the full episode:
    Download
    24144.8K
  31. Every 📧@every
    Every 📧
    RT @RandyCounsman: I used Fred's pitch deck skill with a very basic "here's my movie idea" prompt to have it help me flesh out a concept I've pitched before... And it was genuinely a good creative partner that prompted me with useful questions and research. Got my one-line idea into a full pitch
    Natalia @NataliaZarina
    . @fredgraver is a legend! I learned so much from this conversation and am excited to try his version of compounding: Compound-Producing Want to use AI to produce like Fred? Try his skill here:
    010427
  32. Every 📧@every
    “Don’t freak out, I cloned you.” That’s what @hammer_mt told @nataliazarina after distilling a year of her Slack messages into a natalia.md file describing how she thinks and makes decisions. He then asked an AI to use that file to critique a client email as Natalia would. Using SynthTeam, an open-source library that turns someone’s Slack history into a persona file, he had Codex pull a year of Natalia’s messages from public channels. He looked for situations where she’d made decisions and reverse-engineered how she made them. Read the full piece:
    Download
    45214.6K
  33. Every 📧@every
    Every 📧
    RT @NataliaZarina: . @fredgraver is a legend! I learned so much from this conversation and am excited to try his version of compounding: Compound-Producing Want to use AI to produce like Fred? Try his skill here:
    Every 📧 @every
    Can AI create good art? @fredgraver thinks the answer depends on you. The Emmy Award–winning writer, producer, and founder of AI Writer’s Studio says AI can help with many parts of the creative process—but it can’t give you something to say. On this week’s episode of The Every Podcast, @NataliaZarina sits down with Graver. They discuss: • Why every writer should have a ‘who I am as a writer’ document. • The cast of AI collaborators he’s built into his own writers’ room. • The human quirks that make characters endearing—the part he insists AI can’t supply. Timestamps: 0:00 Introduction 1:37 Fred's path from National Lampoon and Letterman to Twitter and Microsoft 9:39 The "I want in" instinct behind every career pivot 15:11 How Best Week Ever and Metallica taught Fred to build with the audience 18:53 Using AI as a virtual writers' room, not a ghostwriter 24:07 Codifying industry expertise and studio culture into an AI core 28:36 The three phases of making entertainment with AI 33:37 Why you should brain-dump your idea before opening AI 46:47 Fred's thesis: Success is knowing what the audience wants before it does 52:12 Fred's day-to-day workflow across Claude, ChatGPT, and NotebookLM
    050402
  35. Every 📧@every
    Can AI create good art? @fredgraver thinks the answer depends on you. The Emmy Award–winning writer, producer, and founder of AI Writer’s Studio says AI can help with many parts of the creative process—but it can’t give you something to say. On this week’s episode of The Every Podcast, @NataliaZarina sits down with Graver. They discuss: • Why every writer should have a ‘who I am as a writer’ document. • The cast of AI collaborators he’s built into his own writers’ room. • The human quirks that make characters endearing—the part he insists AI can’t supply. Timestamps: 0:00 Introduction 1:37 Fred's path from National Lampoon and Letterman to Twitter and Microsoft 9:39 The "I want in" instinct behind every career pivot 15:11 How Best Week Ever and Metallica taught Fred to build with the audience 18:53 Using AI as a virtual writers' room, not a ghostwriter 24:07 Codifying industry expertise and studio culture into an AI core 28:36 The three phases of making entertainment with AI 33:37 Why you should brain-dump your idea before opening AI 46:47 Fred's thesis: Success is knowing what the audience wants before it does 52:12 Fred's day-to-day workflow across Claude, ChatGPT, and NotebookLM
    Download
    13135.3K
  36. Every 📧@every
    Getting an AI-built prototype to work once is only the beginning. @JannikJung helps turn experiments into software the team can rely on. That means making decisions about code structure, libraries, deployment, and how the project will be maintained. Watch the full episode:
    Download
    1383.1K
  37. Every 📧@every
    This week on Every’s Frontier team: • @hammer_mt rewrote one headline and took simulated agent citations from 2 out of 240 sessions to 240 out of 240. • Mike tested whether agents would wait for a slow API. One waited 30 seconds in all 20 trials—but most agents never tried it. • Mike used LLM neurons to make memes measurable and trace their family tree. • Mike tested whether AI could anticipate @danshipper’s points. Given 400 guesses, it covered 93%—picking the right guess is still unsolved. • @RandyCounsman edited an entire Every Podcast episode in Everycut, the video editor built by @kieranklaassen. • @kplikethebird built a home for Frontier Writing and hired an AI idea scout to find fresh angles in Every’s Slack. • Mike mapped all 1,469 Every essays in 3D and turned gaps between topics into new article pitches. • Mike had three models take turns improving one writing skill. Its win rate against a comparison skill rose from 18% to 100% in an initial 4-round run; a later solo-model control matched the tuning score. • Mike ran Claude until it was using 46 GB of memory. Dan offered a spare Mac mini—with 16 GB of RAM.
    Download
    61152.8K
  38. Every 📧@every
    How to write well with AI: Know your reader. @kplikethebird is adding audience.md to Compound Writing, alongside its voice.md and style.md. For her Working Overtime column, that means checking whether a draft welcomes the AI-curious reader while giving the experienced operator enough practical detail. Watch the full episode:
    Download
    02192.2K
  39. Every 📧@every
    Posts @every
    More from Every’s Frontier team—what we’re building, testing, and learning with AI:
    000497
  41. Every 📧@every
    Taste in an age of AI may depend on materials intelligence, or MQ: an appreciation of the raw materials and techniques behind a finished product, argues @smc90 for her Thesis Statement. Think textiles and stitches, powder coatings, digital textures, or the enamel technique used in a piece of jewelry. The designer’s name and the story of who wore it give an object some meaning, but so does the mood board that inspired it or the behind-the-scenes photo of the process. Her bet: As AI commoditizes more of the surrounding work, materials carry human expertise that has accumulated and has been sustained over centuries. Read Sonal’s full Thesis Statement:
    Download
    22123.6K
  42. Every 📧@every
    Too many browser tabs sent @jackcheng down an unexpected path: building his own browser. It has no tabs, an agent pane for editing with different models, and a peek mode for looking something up without losing his place. A small example of what becomes possible when you can change the application around your workflow. Watch the full episode:
    Download
    10141.9K
  43. Every 📧@every
    When our daily @OpenAI credit use jumped 230%, a strict token budget felt like the obvious answer. But our head of ops Arielle Shipper instead chose to manage our tokens through 3 questions instead: What did it cost? What did it buy us? What did we learn? Read the full piece:
    Download
    0161.8K
  44. Every 📧@every
    Earlier this year, every teammate had a personal agent. Then none of us wanted to keep fixing and updating them. So we shifted to building a shared agent, relying on @AnthropicAI’s Claude Managed Agents infrastructure. @paridhitweets helped build the first version of the Every Agent that went live within a week. Now that the hard part was handled by Anthropic, we could focus on the parts that made the Every Agent more like a coworker: how it behaves, when it should stay quiet, and which connections each teammate can use. Security-wise, credentials stay out of the agent’s view, and changes to shared skills require human approval. There are some trade-offs: We’re tied to Claude, and persistent conversation history means the platform doesn’t support zero-data retention. Install the Every Agent: Read more on our experience building the Every Agent on Claude Managed Agents:
    Download
    70172K
  45. Every 📧@every
    This week at Every: • @RandyCounsman edited an entire Every Podcast episode in Everycut, the video editor built by @kieranklaassen. • @kieranklaassen crossed 20,000 followers on X. • @hammer_mt rewrote one headline and took simulated agent citations from 2 out of 240 sessions to 240 out of 240. • Our ops team wrapped up months of work to get Every collecting sales tax in three more states: New York, Ohio, and Maryland. • @danshipper personally replied to readers who filled out our survey—and had a post featured by LinkedIn News. • Yash Poojary and @beckyisj skipped the App Store and built their own apps with Claude. • The Thesis crew entered the home stretch of preparing our conference on work and AI. • Grant Harvey joined Every to write the daily edition of Context Window. • Arielle Shipper hosted a Women in AI night with women from across the team—and one special guest, Leo.
    Download
    0571.7K
  46. Every 📧@every
    Rare air.
    Shane Hegde @shanehegde
    Next week I'll be at @every's Thesis 27 where 400 founders, executives, and builders will get together to talk about what great human work looks like after automation. Excited to speak about who wins when creative work gets faster.
    01121.6K
  47. Shane Hegde✓@shanehegde
    Next week I'll be at @every's Thesis 27 where 400 founders, executives, and builders will get together to talk about what great human work looks like after automation. Excited to speak about who wins when creative work gets faster.
    Download
    05213.9K